Centre dedocumentation
scientifique

Dépouillements

Modelling fuzzy topological relations between uncertain objects in a GIS / Wei Shi in Photogrammetric Engineering & Remote Sensing, PERS, vol 70 n° 8 (August 2004)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 70 n° 8 (August 2004) . - pp 921 - 929 Titre : Modelling fuzzy topological relations between uncertain objects in a GIS Type de document : Article/Communication Auteurs : Wei Shi, Auteur ; K. Liu, Auteur Année de publication : 2004 Article en page(s) : pp 921 - 929 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] analyse des correspondances [Termes IGN] correction géométrique [Termes IGN] logique floue [Termes IGN] modèle numérique [Termes IGN] objet flou [Termes IGN] objet géographique [Termes IGN] relation floue [Termes IGN] relation topologique [Termes IGN] système d'information géographique Résumé : (Auteur) This paper presents a study on modeling fuzzy topological relations between uncertain objects in GIS. Quasi-coincidence and quasi-difference, which are used to distinguish the topological relations between fuzzy objects, and to indicate the effect of one fuzzy object on another in a fuzzy topology adopted for the development. Geometrically, features in GIS can be classified as point features, linear features, and polygon or region features. In this paper, we first introduce several basic concepts in fuzzy topology that will be used in this study. This is followed by several definitions of fuzzy points, fuzzy lines, and fuzzy regions for GIS objects. Next, the level at which one fuzzy object affects the other is modeled based on the sum and difference of the membership functions that are quasi-coincident and quasi-different, respectively. Finally, an applicable example of using quasi-coincidence and quasi-difference based on the new definitions of fuzzy point, line and polygon is given. Numéro de notice : A2004-307 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article DOI : 10.14358/PERS.70.8.921 En ligne : https://doi.org/10.14358/PERS.70.8.921 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26834 [article]

Assessment of a semantic statistical approach to detecting land covers change using inconsistent data sets / A. Comber in Photogrammetric Engineering & Remote Sensing, PERS, vol 70 n° 8 (August 2004)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 70 n° 8 (August 2004) . - pp 931 - 938 Titre : Assessment of a semantic statistical approach to detecting land covers change using inconsistent data sets Type de document : Article/Communication Auteurs : A. Comber, Auteur ; P. Fischer, Auteur ; R. Wadsworth, Auteur Année de publication : 2004 Article en page(s) : pp 931 - 938 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] analyse diachronique [Termes IGN] base de données d'occupation du sol [Termes IGN] classification dirigée [Termes IGN] détection de changement [Termes IGN] données de terrain [Termes IGN] interopérabilité sémantique [Termes IGN] jeu de données localisées [Termes IGN] métadonnées géographiques [Termes IGN] occupation du sol [Termes IGN] ontologie [Termes IGN] Royaume-Uni [Termes IGN] statistique descriptive Résumé : (Auteur) A semantic, statistical approach to reconciling data with different ontologies is introduced. It was applied to UK land cover datasets from 1990 and 2000 in order to identify land cover change. The approach combined expression of expert opinion about how the semantics of the two datasets relate with spectral homogeneity metadata. A sample of the changes identified was assessed by field validation. Change was identified in 41 percent of the visited parcels, and all of the false positives were found to be due to classification error in either dataset. Thus, the approach reliably identifies inconsistency between two datasets, and the results indicate the suitability of uncertainty formalisms. The inclusion of extensive object-level metadata by the data producers greatly facilitates practical solutions to problems of data interoperability. Numéro de notice : A2004-308 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.70.8.931 En ligne : https://doi.org/10.14358/PERS.70.8.931 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26835 [article]

Uncertainty and confidence in land cover classification using a hybrid classifier approach / W. Liu in Photogrammetric Engineering & Remote Sensing, PERS, vol 70 n° 8 (August 2004)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 70 n° 8 (August 2004) . - pp 963 - 971 Titre : Uncertainty and confidence in land cover classification using a hybrid classifier approach Type de document : Article/Communication Auteurs : W. Liu, Auteur ; Sucharita Gopal, Auteur ; Curtis E. Woodcock, Auteur Année de publication : 2004 Article en page(s) : pp 963 - 971 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] Amérique du nord [Termes IGN] classification hybride [Termes IGN] classification par arbre de décision [Termes IGN] classification par réseau neuronal [Termes IGN] image NOAA-AVHRR [Termes IGN] incertitude des données [Termes IGN] occupation du sol Résumé : (Auteur) Traditional methods of land cover classification and mapping are limited in providing spatial data on the uncertainty of map labels. In this paper, we present a hybrid classifier approach using Decision Tree (DT) and ARTMAP neural network to providing confidence or uncertainty information via majority voting and other rules. The hybrid classifier is tested with AVHRR data to mapping land cover of North America. The two classifiers (DT and ARTMAP) tend to make predictive errors in different contexts. They show 68% agreement in classifying land cover of North America. A set of rules is developed to assign class labels for pixels where the two classifiers disagree. Levels of confidence in the hybrid classification derived from their individual voting (ARTmAP) and probability (DT) are used to assign confidence. The approach outlined in this paper produces two products a hybrid classification map as well as a confidence map based on the two classification schemes. The hybrid approach seems suitable to tackle a variety of classification problems in remote sensing and may ultimately aid map users in making more informed decisions. Numéro de notice : A2004-309 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.70.8.963 En ligne : https://doi.org/10.14358/PERS.70.8.963 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26836 [article]

Supporting quality-based image retrieval through user preference learning / Giorgos Mountrakis in Photogrammetric Engineering & Remote Sensing, PERS, vol 70 n° 8 (August 2004)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 70 n° 8 (August 2004) . - pp 973 - 981 Titre : Supporting quality-based image retrieval through user preference learning Type de document : Article/Communication Auteurs : Giorgos Mountrakis, Auteur ; A. Stefanidis, Auteur ; et al., Auteur Année de publication : 2004 Article en page(s) : pp 973 - 981 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes IGN] apprentissage automatique [Termes IGN] indicateur de qualité [Termes IGN] intelligence artificielle [Termes IGN] qualité d'image [Termes IGN] requête spatiale [Termes IGN] spécification de contenu [Termes IGN] spécification de produit [Termes IGN] utilisateur [Termes IGN] visualisation Résumé : (Auteur) It is common for modern geospatial libraries to contain multiple datasets that cover the same area but differ only in some specific quality attributes (e.g., resolution and precision). This is affecting the concept of content-based geospatial queries, as simple coverage-based query mechanisms (e.g., declaring a specific area of interest) as well as theme-based query mechanisms (e.g., requesting a black and white aerial photo or multispectral satellite imagery) are rendered inadequate to identify and access specific datasets in such collections. In this paper we introduce a novel approach to handle data quality attributes in geospatial queries. Our approach is characterized by the ability to model and learn user preferences, thus establishing user profiles that allow us to customize image queries for improving their functionality in a constantly diversifying geospatial user community. Numéro de notice : A2004-310 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.14358/PERS.70.8.973 En ligne : https://doi.org/10.14358/PERS.70.8.973 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26837 [article]